Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Claude Code Routines

code.claude.com

Post reply on HN
Print view View original

181–190 of 451 posts

Re: Claude Code Routines

#181

Post by freedomben »

joshstrange wrote: post #66

LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…

This echoes my thoughts exactly. I've tried to stay model-agnostic but the nudges and shoves from Anthropic continue to make that a challenge. No way I'm going that deep into their "cloud" services, unless it's a portable standard. I did MCP and skills because those were transferrable.

I also clearly see the lock-in/moat strategy playing out here, and I don't like it. It's classic SV tactics. I've been burned too many times to let it happen again if I can help it.

Re: Claude Code Routines

#182

Post by phist_mcgee »

JohnMakin wrote: post #134
joshstrange wrote: post #66

LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…

This is a similar sentiment I heard early on in the cloud adoption fever, many companies hedged by being “multi cloud” which ended up mostly being abandoned due to hostile patterns by cloud providers, and a lot of cost. Ultimately it didn’t really end up mattering and the most dire predictions of vendor lock in abuse didn’t really happen as feared (I know people will disagree with this, but specifically speaking abou…

Let's see how it shakes out after Athropic and OpenAI fully stop subsidizing their plans, that may alter the calculus.

Re: Claude Code Routines

#183

Post by nine_k »

Readerium wrote: post #172
nine_k wrote: post #163

Earlier quoted context omitted.

In this regard, the release of open-weight Gemma models that can run on reasonable local hardware, and are not drastically worse than Anthropic flagships, is quite a punch. An M2 Mac Mini with 32GB is about 10 months worth of Claude Max subscription.

In coding they are worse. Chinese models (GLM, MiniMax) are better.

Anyway, there are a few model that are freely distributable, and that can reasonably run on consumer-grade local hardware.

It changes a number of things. Not all tasks require very high intelligence, but a lot of data may be sensitive enough to avoid sharing it with a third party.

Re: Claude Code Routines

#184

Post by jeppester »

joshstrange wrote: post #66

LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…

I always hated SEO because it was not an exact science - like programming was.

Too bad we've now managed to turn programming into the same annoying guesswork.

Re: Claude Code Routines

#185

Post by fragmede »

michaeldwan wrote: post #147
JohnMakin wrote: post #134

Earlier quoted context omitted.

This is a similar sentiment I heard early on in the cloud adoption fever, many companies hedged by being “multi cloud” which ended up mostly being abandoned due to hostile patterns by cloud providers, and a lot of cost. Ultimately it didn’t really end up mattering and the most dire predictions of vendor lock in abuse didn’t really happen as feared (I know people will disagree with this, but specifically speaking abou…

I credit containerization, k8s, and terraform for preventing vendor lock in. Compute like EC2 or GCE are effectively interoperable. Ditto for managed services for k8s or Postgres. The new products Anthropic is shipping is more like Lambda. Vendor kool-aid lots of people will buy into. What grinds my gears is how Anthropic is actively avoiding standards. Like being the only harness that doesn't read AGENTS.md. I work…

There's a tiny amount of friction. Enough that I'll be honest and say that I spend the majority of my time with one vendor's system, but compared the to the fiction of moving from one cloud to another, eg AWS to GCP, the friction between opening Claude code vs codex is basically zero. Have an active subscription and have Claude.md say "read Agents.md".

Claude Code routines sounds useful, but at the same time, under AI-codepocalypse, my guess is it would take an afternoon to have codex reimplement it using some existing freemium SaaS Cron platform, assuming I didn't want to roll my own (because of the maintenance overhead vs paying someone else to deal with that).

Re: Claude Code Routines

#186

Post by twobitshifter »

It seemed OpenClaw is just Pi with Cron and hooks, and it seems like this is just Claude Code with Cron and hooks. Based on the superiority of Pi, I would not expect this to attract any one from OpenClaw, but it will increase token usage in Claude Code.

Re: Claude Code Routines

#187

Post by freedomben »

gardenhedge wrote: post #95
palata wrote: post #93

Earlier quoted context omitted.

> - No trust that they won't nerf the tool/model behind the feature I actually trust that they will.

Yeah, I build my workflows with two things in mind: 1) that AI will be more advanced in the future 2) that the AI I am using will be worse in the future

Same! I actually have some comments in my codebase now like this one:

    # Note:  This is inefficient, but deterministic and predictable.  Previous
             attempts at improvements led to hard-to-predict bugs and were
             scrapped.  TODO improve this function when AI gets better
I don't love it or even like it, but it is realistic.

Re: Claude Code Routines

#188

Post by alfalfasprout »

joshstrange wrote: post #66

LLMs and LLM providers are massive black boxes. I get a lot of value from them and so I can put up with that to a certain extent, but these new "products"/features that Anthropic are shipping are very unappealing to me. Not because I can't see a use-case for them, but because I have 0 trust in them: - No trust that they won't nerf the tool/model behind the feature - No trust they won't sunset the feature (the graveya…

Yep. Trust is easy to lose, hard to earn. A nondeterministic black box that is likely buggy, will almost certainly change, and has a likelihood of getting enshittified is not a very good value proposition to build on top of or invest in.

Increasingly, we're also seeing the moat shrink somewhat. Frontier models are converging in performance (and I bet even Mythos will get matched) and harnesses are improving too across the board (OpenCode and Codex for example).

I get why they're trying to do that (a perception of a moat bloats the IPO price) but I have little faith there's any real moat at all (especially as competitors are still flush with cash).

Re: Claude Code Routines

#189

Post by stavros »

joshstrange wrote: post #60
taytus wrote: post #48

Earlier quoted context omitted.

They are not dumb restrictions. They just don't have the compute. That is the dumb part. Dario did not secure the compute they need so now they are obviously struggling.

The restrictions are dumb not because they're lower than any of us want them to be, but because they're unclear. Every time Claude comes up on Hacker News, someone asks this question. And every time people chime in to agree that they also are unclear or someone weighs in saying, no, it's totally clear, while proceeding not to point at any official resource and/or to "explain" the rules in a that is incompatible with…

There's another part that's bullshit: If you've paid for an annual subscription, for a given number of tokens, welp, now you're getting fewer tokens. They've decreased the limits mid-subscription. How is it not bait-and-switch to pay for something for a year only to have something else delivered?

Re: Claude Code Routines

#190

Post by titzer »

Eldodi wrote: post #49

Anthropic is really good at releasing features that are almost the same but not exactly the same as other features they released the week before

Just wait until they get into the phase where they're big enough that they're eating all the baby startups and have to pick winners and losers amongst the myriad of overlapping features while also having the previous baby startups they acquired crank out new features.

We're watching a speed run of growthism, folks.

Post reply on HN